def smallcatGBM():
# Training set has 26 categories from A to Z
# Categories A, C, E, G, ... are perfect predictors of y = 1
# Categories B, D, F, H, ... are perfect predictors of y = 0
#Log.info("Importing alphabet_cattest.csv data...\n")
alphabet = h2o.import_file(path=tests.locate("smalldata/gbm_test/alphabet_cattest.csv"))
alphabet["y"] = alphabet["y"].asfactor()
#Log.info("Summary of alphabet_cattest.csv from H2O:\n")
#alphabet.summary()
# Prepare data for scikit use
trainData = np.loadtxt(tests.locate("smalldata/gbm_test/alphabet_cattest.csv"), delimiter=',', skiprows=1,
converters={0:lambda s: ord(s.split("\"")[1])})
trainDataResponse = trainData[:,1]
trainDataFeatures = trainData[:,0]
# Train H2O GBM Model:
#Log.info("H2O GBM (Naive Split) with parameters:\nntrees = 1, max_depth = 1, nbins = 100\n")
gbm_h2o = h2o.gbm(x=alphabet[['X']], y=alphabet["y"], distribution="bernoulli", ntrees=1, max_depth=1, nbins=100)
gbm_h2o.show()
# Train scikit GBM Model:
# Log.info("scikit GBM with same parameters:")
gbm_sci = ensemble.GradientBoostingClassifier(n_estimators=1, max_depth=1, max_features=None)
gbm_sci.fit(trainDataFeatures[:,np.newaxis],trainDataResponse)
def dim_checks():
# Log.info("Uploading logreg/princeton/cuse.dat")
h2o_data = h2o.import_file(path=tests.locate("smalldata/logreg/prostate.csv"))
np_data = np.loadtxt(tests.locate("smalldata/logreg/prostate.csv"), delimiter=',', skiprows=1)
h2o_rows, h2o_cols = h2o_data.dim
np_rows, np_cols = list(np_data.shape)
print 'The dimensions of h2o frame is: {0} x {1}'.format(h2o_rows, h2o_cols)
print 'The dimensions of numpy array is: {0} x {1}'.format(np_rows, np_cols)
assert [h2o_rows, h2o_cols] == [np_rows, np_cols], "expected equal number of columns and rows"
# Log.info("Slice out a column and data frame it, try dim on it...")
h2o_slice = h2o_data[4]
np_slice = np_data[:,4]
h2o_rows, h2o_cols = h2o_slice.dim
np_rows = np_slice.shape[0]
print 'The dimensions of h2o column slice is: {0} x {1}'.format(h2o_rows, h2o_cols)
print 'The dimensions of numpy array column slice is: {0} x 1'.format(np_rows)
assert [h2o_rows, h2o_cols] == [np_rows, 1], "expected equal number of columns and rows"
# Log.info("OK, now try an operator, e.g. '&', and then check dimensions agao...")
h2oColAmpFive = h2o_slice & 5
assert h2oColAmpFive.nrow == h2o_rows, "expected the number of rows to remain unchanged"
def link_functions_binomial():
print("Read in prostate data.")
h2o_data = h2o.import_file(path=tests.locate("smalldata/prostate/prostate_complete.csv.zip"))
h2o_data.head()
sm_data = pd.read_csv(zipfile.ZipFile(tests.locate("smalldata/prostate/prostate_complete.csv.zip")).open("prostate_complete.csv")).as_matrix()
sm_data_response = sm_data[:,2]
sm_data_features = sm_data[:,[1,3,4,5,6,7,8,9]]
print("Testing for family: BINOMIAL")
print("Set variables for h2o.")
myY = "CAPSULE"
myX = ["ID","AGE","RACE","GLEASON","DCAPS","PSA","VOL","DPROS"]
print("Create models with canonical link: LOGIT")
h2o_model = h2o.glm(x=h2o_data[myX], y=h2o_data[myY].asfactor(), family="binomial", link="logit",alpha=[0.5], Lambda=[0])
sm_model = sm.GLM(endog=sm_data_response, exog=sm_data_features, family=sm.families.Binomial(sm.families.links.logit)).fit()
print("Compare model deviances for link function logit")
h2o_deviance = h2o_model.residual_deviance() / h2o_model.null_deviance()
sm_deviance = sm_model.deviance / sm_model.null_deviance
assert h2o_deviance - sm_deviance < 0.01, "expected h2o to have an equivalent or better deviance measures"
def deeplearning_demo():
# Training data
train_data = h2o.import_file(
path=tests.locate("smalldata/gbm_test/ecology_model.csv"))
train_data = train_data.drop('Site')
train_data['Angaus'] = train_data['Angaus'].asfactor()
print train_data.describe()
train_data.head()
# Testing data
test_data = h2o.import_file(
path=tests.locate("smalldata/gbm_test/ecology_eval.csv"))
test_data['Angaus'] = test_data['Angaus'].asfactor()
print test_data.describe()
test_data.head()
# Run DeepLearning
dl = H2ODeepLearningEstimator(loss="CrossEntropy",
epochs=1000,
hidden=[20, 20, 20])
dl.train(x=range(1, train_data.ncol),
y="Angaus",
training_frame=train_data,
validation_frame=test_data)
dl.show()
def benignKmeans():
# Connect to a pre-existing cluster
# connect to localhost:54321
# Log.info("Importing benign.csv data...\n")
benign_h2o = h2o.import_file(
path=tests.locate("smalldata/logreg/benign.csv"))
#benign_h2o.summary()
benign_sci = np.genfromtxt(tests.locate("smalldata/logreg/benign.csv"),
delimiter=",")
# Impute missing values with column mean
imp = Imputer(missing_values='NaN', strategy='mean', axis=0)
benign_sci = imp.fit_transform(benign_sci)
# Log.info(paste("H2O K-Means with ", i, " clusters:\n", sep = ""))
for i in range(1, 7):
benign_h2o_km = h2o.kmeans(x=benign_h2o, k=i)
print "H2O centers"
print benign_h2o_km.centers()
benign_sci_km = KMeans(n_clusters=i, init='k-means++', n_init=1)
benign_sci_km.fit(benign_sci)
print "sckit centers"
print benign_sci_km.cluster_centers_
def link_functions_gaussian():
print("Read in prostate data.")
h2o_data = h2o.import_file(
path=tests.locate("smalldata/prostate/prostate_complete.csv.zip"))
h2o_data.head()
sm_data = pd.read_csv(
zipfile.ZipFile(
tests.locate("smalldata/prostate/prostate_complete.csv.zip")).open(
"prostate_complete.csv")).as_matrix()
sm_data_response = sm_data[:, 9]
sm_data_features = sm_data[:, 1:9]
print("Testing for family: GAUSSIAN")
print("Set variables for h2o.")
myY = "GLEASON"
myX = ["ID", "AGE", "RACE", "CAPSULE", "DCAPS", "PSA", "VOL", "DPROS"]
print("Create models with canonical link: IDENTITY")
h2o_model = h2o.glm(x=h2o_data[myX],
y=h2o_data[myY],
family="gaussian",
link="identity",
alpha=[0.5],
Lambda=[0])
sm_model = sm.GLM(endog=sm_data_response,
exog=sm_data_features,
family=sm.families.Gaussian(
sm.families.links.identity)).fit()
print("Compare model deviances for link function identity")
h2o_deviance = h2o_model.residual_deviance() / h2o_model.null_deviance()
sm_deviance = sm_model.deviance / sm_model.null_deviance
assert h2o_deviance - sm_deviance < 0.01, "expected h2o to have an equivalent or better deviance measures"
def group_by():
# Connect to a pre-existing cluster
h2o_iris = h2o.import_file(
path=tests.locate("smalldata/iris/iris_wheader.csv"))
pd_iris = pd.read_csv(tests.locate("smalldata/iris/iris_wheader.csv"))
na_handling = ["ignore", "rm", "all"]
col_names = h2o_iris.col_names[0:4]
print "Running smoke test"
# smoke test
for na in na_handling:
grouped = h2o_iris.group_by("class")
grouped \
.count(na=na) \
.min( na=na) \
.max( na=na) \
.mean( na=na) \
.var( na=na) \
.sd( na=na) \
.ss( na=na) \
.sum( na=na)
print grouped.get_frame()
def additional_parameters():
#col_types as list
dest_frame="dev29&hex%"
c_names = ["a", "b", "c"]
c_types = ["enum", "enum", "string"]
fhex = h2o.import_file(tests.locate("smalldata/jira/hexdev_29.csv"),
destination_frame=dest_frame,
col_names=c_names,
col_types=c_types)
fhex.describe()
assert fhex._id == dest_frame.replace("%",".").replace("&",".")
assert fhex.col_names == c_names
col_summary = h2o.frame(fhex._id)["frames"][0]["columns"]
for i in range(len(col_summary)):
assert col_summary[i]["type"] == c_types[i]
#col_types as dictionary
dest_frame="dev29&hex%"
c_names = ["a", "b", "c"]
c_types = {"c":"string", "a":"enum", "b": "enum"}
fhex = h2o.import_file(tests.locate("smalldata/jira/hexdev_29.csv"),
destination_frame=dest_frame,
col_names=c_names,
col_types=c_types)
fhex.describe()
assert fhex._id == dest_frame.replace("%",".").replace("&",".")
assert fhex.col_names == c_names
col_summary = h2o.frame(fhex._id)["frames"][0]["columns"]
for i in range(len(col_summary)):
assert col_summary[i]["type"] == c_types[c_names[i]]
def plot_test():
kwargs = {}
kwargs['server'] = True
air = h2o.import_file(tests.locate("smalldata/airlines/AirlinesTrain.csv.zip"))
# Constructing test and train sets by sampling (20/80)
s = air[0].runif()
air_train = air[s <= 0.8]
air_valid = air[s > 0.8]
myX = ["Origin", "Dest", "Distance", "UniqueCarrier", "fMonth", "fDayofMonth", "fDayOfWeek"]
myY = "IsDepDelayed"
air_gbm = h2o.gbm(x=air_train[myX], y=air_train[myY], validation_x=air_valid[myX], validation_y=air_valid[myY],
distribution="bernoulli", ntrees=100, max_depth=3, learn_rate=0.01)
# Plot ROC for training and validation sets
air_gbm.plot(type="roc", train=True, **kwargs)
air_gbm.plot(type="roc", valid=True, **kwargs)
air_test = h2o.import_file(tests.locate("smalldata/airlines/AirlinesTest.csv.zip"))
perf = air_gbm.model_performance(air_test)
#Plot ROC for test set
perf.plot(type="roc", **kwargs)
def fiftycatGBM():
# Training set has only 45 categories cat1 through cat45
#Log.info("Importing 50_cattest_train.csv data...\n")
train = h2o.import_file(path=tests.locate("smalldata/gbm_test/50_cattest_train.csv"))
train["y"] = train["y"].asfactor()
#Log.info("Summary of 50_cattest_train.csv from H2O:\n")
#train.summary()
# Train H2O GBM Model:
#Log.info(paste("H2O GBM with parameters:\nntrees = 10, max_depth = 20, nbins = 20\n", sep = ""))
model = h2o.gbm(x=train[["x1","x2"]], y=train["y"], distribution="bernoulli", ntrees=10, max_depth=5, nbins=20)
model.show()
# Test dataset has all 50 categories cat1 through cat50
#Log.info("Importing 50_cattest_test.csv data...\n")
test = h2o.import_file(path=tests.locate("smalldata/gbm_test/50_cattest_test.csv"))
#Log.info("Summary of 50_cattest_test.csv from H2O:\n")
#test.summary()
# Predict on test dataset with GBM model:
#Log.info("Performing predictions on test dataset...\n")
predictions = model.predict(test)
predictions.show()
# Get the confusion matrix and AUC
#Log.info("Confusion matrix of predictions (max accuracy):\n")
performance = model.model_performance(test)
test_cm = performance.confusion_matrix()
test_auc = performance.auc()
def pubdev_1953():
# small_test = [tests.locate("bigdata/laptop/citibike-nyc/2013-10.csv")]
# data = h2o.import_file(path=small_test)
# startime = data["starttime"]
# secsPerDay=1000*60*60*24
# data["Days"] = (startime/secsPerDay).floor()
# grouped = data.group_by(["Days","start station name"])
# bpd = grouped.count(name="bikes").get_frame()
# secs = bpd["Days"]*secsPerDay
# bpd["Month"] = secs.month().asfactor()
# bpd["DayOfWeek"] = secs.dayOfWeek()
# wthr1 = h2o.import_file(path=[tests.locate("bigdata/laptop/citibike-nyc/31081_New_York_City__Hourly_2013.csv"), tests.locate("bigdata/laptop/citibike-nyc/31081_New_York_City__Hourly_2014.csv")])
# wthr2 = wthr1[["Year Local","Month Local","Day Local","Hour Local","Dew Point (C)","Humidity Fraction","Precipitation One Hour (mm)","Temperature (C)","Weather Code 1/ Description"]]
# wthr2.set_name(wthr2.index("Precipitation One Hour (mm)"), "Rain (mm)")
# wthr2.set_name(wthr2.index("Weather Code 1/ Description"), "WC1")
# wthr3 = wthr2[ wthr2["Hour Local"]==12 ]
# wthr3["msec"] = h2o.H2OFrame.mktime(year=wthr3["Year Local"], month=wthr3["Month Local"]-1, day=wthr3["Day Local"]-1, hour=wthr3["Hour Local"])
# secsPerDay=1000*60*60*24
# wthr3["Days"] = (wthr3["msec"]/secsPerDay).floor()
# wthr4 = wthr3.drop("Year Local").drop("Month Local").drop("Day Local").drop("Hour Local").drop("msec")
# rain = wthr4["Rain (mm)"]
# rain[ rain.isna() ] = 0
# bpd_with_weather = bpd.merge(wthr4,allLeft=True,allRite=False)
# r = bpd_with_weather['Days'].runif(seed=356964763)
# train = bpd_with_weather[ r < 0.6]
# test = bpd_with_weather[(0.6 <= r) & (r < 0.9)]
predictors = ['DayOfWeek', 'WC1', 'start station name', 'Temperature (C)', 'Days', 'Month', 'Humidity Fraction', 'Rain (mm)', 'Dew Point (C)']
train = h2o.import_file(tests.locate("smalldata/glm_test/citibike_small_train.csv"))
test = h2o.import_file(tests.locate("smalldata/glm_test/citibike_small_test.csv"))
glm0 = h2o.glm(x=train[predictors], y=train["bikes"], validation_x=test[predictors], validation_y=test["bikes"], family="poisson")
def frame_as_list():
iris = h2o.import_file(path=tests.locate("smalldata/iris/iris_wheader.csv"))
prostate = h2o.import_file(path=tests.locate("smalldata/prostate/prostate.csv.zip"))
airlines = h2o.import_file(path=tests.locate("smalldata/airlines/allyears2k.zip"))
res1 = h2o.as_list(iris, use_pandas=False)
assert (
abs(float(res1[9][0]) - 4.4) < 1e-10
and abs(float(res1[9][1]) - 2.9) < 1e-10
and abs(float(res1[9][2]) - 1.4) < 1e-10
), "incorrect values"
res2 = h2o.as_list(prostate, use_pandas=False)
assert (
abs(float(res2[7][0]) - 7) < 1e-10
and abs(float(res2[7][1]) - 0) < 1e-10
and abs(float(res2[7][2]) - 68) < 1e-10
), "incorrect values"
res3 = h2o.as_list(airlines, use_pandas=False)
assert (
abs(float(res3[4][0]) - 1987) < 1e-10
and abs(float(res3[4][1]) - 10) < 1e-10
and abs(float(res3[4][2]) - 18) < 1e-10
), "incorrect values"
def checkpoint_new_category_in_predictor():
sv1 = h2o.upload_file(tests.locate("smalldata/iris/setosa_versicolor.csv"))
sv2 = h2o.upload_file(tests.locate("smalldata/iris/setosa_versicolor.csv"))
vir = h2o.upload_file(tests.locate("smalldata/iris/virginica.csv"))
m1 = h2o.deeplearning(x=sv1[[0, 1, 2, 4]], y=sv1[3], epochs=100)
m2 = h2o.deeplearning(x=sv2[[0, 1, 2, 4]],
y=sv2[3],
epochs=200,
checkpoint=m1.model_id)
# attempt to continue building model, but with an expanded categorical predictor domain.
# this should fail
try:
m3 = h2o.deeplearning(x=vir[[0, 1, 2, 4]],
y=vir[3],
epochs=200,
checkpoint=m1.model_id)
assert False, "Expected continued model-building to fail with new categories introduced in predictor"
except EnvironmentError:
pass
# attempt to predict on new model, but with observations that have expanded categorical predictor domain.
predictions = m2.predict(vir)
def wide_dataset_large():
print("Reading in Arcene training data for binomial modeling.")
trainDataResponse = np.genfromtxt(tests.locate("smalldata/arcene/arcene_train_labels.labels"), delimiter=' ')
trainDataResponse = np.where(trainDataResponse == -1, 0, 1)
trainDataFeatures = np.genfromtxt(tests.locate("smalldata/arcene/arcene_train.data"), delimiter=' ')
trainData = h2o.H2OFrame(np.column_stack((trainDataResponse, trainDataFeatures)).tolist())
print("Run model on 3250 columns of Arcene with strong rules off.")
model = h2o.glm(x=trainData[1:3250], y=trainData[0].asfactor(), family="binomial", lambda_search=False, alpha=[1])
print("Test model on validation set.")
validDataResponse = np.genfromtxt(tests.locate("smalldata/arcene/arcene_valid_labels.labels"), delimiter=' ')
validDataResponse = np.where(validDataResponse == -1, 0, 1)
validDataFeatures = np.genfromtxt(tests.locate("smalldata/arcene/arcene_valid.data"), delimiter=' ')
validData = h2o.H2OFrame(np.column_stack((validDataResponse, validDataFeatures)).tolist())
prediction = model.predict(validData)
print("Check performance of predictions.")
performance = model.model_performance(validData)
print("Check that prediction AUC better than guessing (0.5).")
assert performance.auc() > 0.5, "predictions should be better then pure chance"
def group_by():
# Connect to a pre-existing cluster
h2o_iris = h2o.import_file(path=tests.locate("smalldata/iris/iris_wheader.csv"))
pd_iris = pd.read_csv(tests.locate("smalldata/iris/iris_wheader.csv"))
na_handling = ["ignore","rm","all"]
col_names = h2o_iris.col_names[0:4]
print "Running smoke test"
# smoke test
for na in na_handling:
grouped = h2o_iris.group_by("class")
grouped \
.count(na=na) \
.min( na=na) \
.max( na=na) \
.mean( na=na) \
.var( na=na) \
.sd( na=na) \
.ss( na=na) \
.sum( na=na)
print grouped.get_frame()
def anomaly():
print "Deep Learning Anomaly Detection MNIST"
train = h2o.import_file(tests.locate("bigdata/laptop/mnist/train.csv.gz"))
test = h2o.import_file(tests.locate("bigdata/laptop/mnist/test.csv.gz"))
predictors = range(0,784)
resp = 784
# unsupervised -> drop the response column (digit: 0-9)
train = train[predictors]
test = test[predictors]
# 1) LEARN WHAT'S NORMAL
# train unsupervised Deep Learning autoencoder model on train_hex
ae_model = h2o.deeplearning(x=train[predictors], training_frame=train, activation="Tanh", autoencoder=True,
hidden=[50], l1=1e-5, ignore_const_cols=False, epochs=1)
# 2) DETECT OUTLIERS
# anomaly app computes the per-row reconstruction error for the test data set
# (passing it through the autoencoder model and computing mean square error (MSE) for each row)
test_rec_error = ae_model.anomaly(test)
# 3) VISUALIZE OUTLIERS
# Let's look at the test set points with low/median/high reconstruction errors.
# We will now visualize the original test set points and their reconstructions obtained
# by propagating them through the narrow neural net.
# Convert the test data into its autoencoded representation (pass through narrow neural net)
test_recon = ae_model.predict(test)
def iris_h2o_vs_sciKmeans():
# Connect to a pre-existing cluster
# connect to localhost:54321
iris_h2o = h2o.import_file(path=tests.locate("smalldata/iris/iris.csv"))
iris_sci = np.genfromtxt(tests.locate("smalldata/iris/iris.csv"), delimiter=',')
iris_sci = iris_sci[:,0:4]
s =[[4.9,3.0,1.4,0.2],
[5.6,2.5,3.9,1.1],
[6.5,3.0,5.2,2.0]]
start = h2o.H2OFrame(s)
h2o_km = h2o.kmeans(x=iris_h2o[0:4], k=3, user_points=start, standardize=False)
sci_km = KMeans(n_clusters=3, init=np.asarray(s), n_init=1)
sci_km.fit(iris_sci)
# Log.info("Cluster centers from H2O:")
print "Cluster centers from H2O:"
h2o_centers = h2o_km.centers()
print h2o_centers
# Log.info("Cluster centers from scikit:")
print "Cluster centers from scikit:"
sci_centers = sci_km.cluster_centers_.tolist()
print sci_centers
for hcenter, scenter in zip(h2o_centers, sci_centers):
for hpoint, spoint in zip(hcenter,scenter):
assert (hpoint- spoint) < 1e-10, "expected centers to be the same"
def javapredict_cars():
# optional parameters
params = {
'ntrees': 5000,
'max_depth': 10,
'min_rows': 1,
'learn_rate': 0.1,
'balance_classes': random.sample([True, False], 1)[0]
}
print "Parameter list:"
for k, v in zip(params.keys(), params.values()):
print "{0}, {1}".format(k, v)
train = h2o.import_file(
tests.locate("smalldata/junit/cars_nice_header.csv"))
test = h2o.import_file(
tests.locate("smalldata/junit/cars_nice_header.csv"))
x = [
"name", "economy", "displacement", "power", "weight", "acceleration",
"year"
]
y = "cylinders"
tests.javapredict("gbm", "numeric", train, test, x, y, **params)
def frame_slicing():
iris = h2o.import_file(path=tests.locate("smalldata/iris/iris_wheader.csv"))
prostate = h2o.import_file(path=tests.locate("smalldata/prostate/prostate.csv.zip"))
airlines = h2o.import_file(path=tests.locate("smalldata/airlines/allyears2k.zip"))
iris.show()
prostate.show()
airlines.show()
###################################################################
# H2OFrame[int] (column slice)
res1 = iris[0]
assert abs(res1[8,:] - 4.4) < 1e-10, "incorrect values"
# H2OFrame[int,int]
res2 = prostate[13, 3]
assert abs(res2 - 1) < 1e-10, "incorrect values"
# H2OFrame[int, slice]
res3 = airlines[12, 0:3]
assert abs(res3[0,0] - 1987) < 1e-10 and abs(res3[0,1] - 10) < 1e-10 and abs(res3[0,2] - 29) < 1e-10, \
"incorrect values"
# H2OFrame[slice, int]
res4 = iris[5:8, 1]
assert abs(res4[0,:] - 3.9) < 1e-10 and abs(res4[1,:] - 3.4) < 1e-10 and abs(res4[2,:] - 3.4) < 1e-10, "incorrect values"
# H2OFrame[slice, slice]
res5 = prostate[5:8, 0:3]
assert abs(res5[0,0] - 6) < 1e-10 and abs(res5[1,1] - 0) < 1e-10 and abs(res5[2,2] - 61) < 1e-10, "incorrect values"
def link_functions_gaussian():
print("Read in prostate data.")
h2o_data = h2o.import_file(path=tests.locate("smalldata/prostate/prostate_complete.csv.zip"))
h2o_data.head()
sm_data = pd.read_csv(zipfile.ZipFile(tests.locate("smalldata/prostate/prostate_complete.csv.zip")).
open("prostate_complete.csv")).as_matrix()
sm_data_response = sm_data[:,9]
sm_data_features = sm_data[:,1:9]
print("Testing for family: GAUSSIAN")
print("Set variables for h2o.")
myY = "GLEASON"
myX = ["ID","AGE","RACE","CAPSULE","DCAPS","PSA","VOL","DPROS"]
print("Create models with canonical link: IDENTITY")
h2o_model = h2o.glm(x=h2o_data[myX], y=h2o_data[myY], family="gaussian", link="identity",alpha=[0.5], Lambda=[0])
sm_model = sm.GLM(endog=sm_data_response, exog=sm_data_features,
family=sm.families.Gaussian(sm.families.links.identity)).fit()
print("Compare model deviances for link function identity")
h2o_deviance = h2o_model.residual_deviance() / h2o_model.null_deviance()
sm_deviance = sm_model.deviance / sm_model.null_deviance
assert h2o_deviance - sm_deviance < 0.01, "expected h2o to have an equivalent or better deviance measures"
def fiftycatRF():
# Training set has only 45 categories cat1 through cat45
#Log.info("Importing 50_cattest_train.csv data...\n")
train = h2o.import_file(path=tests.locate("smalldata/gbm_test/50_cattest_train.csv"))
train["y"] = train["y"].asfactor()
#Log.info("Summary of 50_cattest_train.csv from H2O:\n")
#train.summary()
# Train H2O DRF Model:
#Log.info(paste("H2O DRF with parameters:\nclassification = TRUE, ntree = 50, depth = 20, nbins = 500\n", sep = ""))
model = h2o.random_forest(x=train[["x1", "x2"]], y=train["y"], ntrees=50, max_depth=20, nbins=500)
# Test dataset has all 50 categories cat1 through cat50
#Log.info("Importing 50_cattest_test.csv data...\n")
test = h2o.import_file(path=tests.locate("smalldata/gbm_test/50_cattest_test.csv"))
#Log.info("Summary of 50_cattest_test.csv from H2O:\n")
#test.summary()
# Predict on test dataset with DRF model:
#Log.info("Performing predictions on test dataset...\n")
preds = model.predict(test)
preds.head()
# Get the confusion matrix and AUC
#Log.info("Confusion matrix of predictions (max accuracy):\n")
perf = model.model_performance(test)
perf.show()
cm = perf.confusion_matrix()
print(cm)
def offsets_and_distributions():
# cars
cars = h2o.upload_file(tests.locate("smalldata/junit/cars_20mpg.csv"))
cars = cars[cars["economy_20mpg"].isna() == 0]
cars["economy_20mpg"] = cars["economy_20mpg"].asfactor()
offset = h2o.H2OFrame(python_obj=[[.5] for x in range(398)])
offset.set_name(0,"x1")
cars = cars.cbind(offset)
# insurance
insurance = h2o.import_file(tests.locate("smalldata/glm_test/insurance.csv"))
insurance["offset"] = insurance["Holders"].log()
# bernoulli - offset not supported
#dl = h2o.deeplearning(x=cars[2:8], y=cars["economy_20mpg"], distribution="bernoulli", offset_column="x1",
# training_frame=cars)
#predictions = dl.predict(cars)
# gamma
dl = h2o.deeplearning(x=insurance[0:3], y=insurance["Claims"], distribution="gamma", offset_column="offset", training_frame=insurance)
predictions = dl.predict(insurance)
# gaussian
dl = h2o.deeplearning(x=insurance[0:3], y=insurance["Claims"], distribution="gaussian", offset_column="offset", training_frame=insurance)
predictions = dl.predict(insurance)
# poisson
dl = h2o.deeplearning(x=insurance[0:3], y=insurance["Claims"], distribution="poisson", offset_column="offset", training_frame=insurance)
predictions = dl.predict(insurance)
# tweedie
dl = h2o.deeplearning(x=insurance.names[0:3], y="Claims", distribution="tweedie", offset_column="offset", training_frame=insurance)
predictions = dl.predict(insurance)
def col_names_check():
iris_wheader = h2o.import_file(tests.locate("smalldata/iris/iris_wheader.csv"))
assert iris_wheader.col_names == ["sepal_len","sepal_wid","petal_len","petal_wid","class"], \
"Expected {0} for column names but got {1}".format(["sepal_len","sepal_wid","petal_len","petal_wid","class"],
iris_wheader.col_names)
iris = h2o.import_file(tests.locate("smalldata/iris/iris.csv"))
assert iris.col_names == ["C1","C2","C3","C4","C5"], "Expected {0} for column names but got " \
"{1}".format(["C1","C2","C3","C4","C5"], iris.col_names)
df = h2o.H2OFrame(np.random.randn(100,4).tolist(), column_names=list("ABCD"), column_types=["Enum"]*4)
df.head()
assert df.col_names == list("ABCD"), "Expected {} for column names but got {}".format(list("ABCD"), df.col_names)
assert df.types == {"A": "Enum", "C": "Enum", "B": "Enum", "D": "Enum"}, "Expected {} for column types " \
"but got {}".format({"A": "Enum", "C": "Enum", "B": "Enum", "D": "Enum"},
df.types)
df = h2o.H2OFrame(np.random.randn(100,4).tolist())
df.head()
assert df.col_names == ["C1","C2","C3","C4"], "Expected {} for column names but got {}".format(["C1","C2","C3","C4"]
, df.col_names)
assert df.types == {"C3": "Numeric", "C2": "Numeric", "C1": "Numeric", "C4": "Numeric"}, "Expected {}" \
" for column types but got {}".format({"C3": "Numeric", "C2": "Numeric", "C1": "Numeric",
"C4": "Numeric"}, df.types)
def hit_ratio_test():
air_train = h2o.import_file(
path=tests.locate("smalldata/airlines/AirlinesTrain.csv.zip"))
air_valid = h2o.import_file(
path=tests.locate("smalldata/airlines/AirlinesTest.csv.zip"))
air_test = h2o.import_file(
path=tests.locate("smalldata/airlines/AirlinesTest.csv.zip"))
gbm_mult = h2o.gbm(x=air_train[[
"Origin", "Dest", "Distance", "UniqueCarrier", "IsDepDelayed",
"fDayofMonth", "fMonth"
]],
y=air_train["fDayOfWeek"].asfactor(),
validation_x=air_valid[[
"Origin", "Dest", "Distance", "UniqueCarrier",
"IsDepDelayed", "fDayofMonth", "fMonth"
]],
validation_y=air_valid["fDayOfWeek"].asfactor(),
distribution="multinomial")
training_hit_ratio_table = gbm_mult.hit_ratio_table(train=True)
training_hit_ratio_table.show()
validation_hit_ratio_table = gbm_mult.hit_ratio_table(valid=True)
validation_hit_ratio_table.show()
perf = gbm_mult.model_performance(air_test)
test_hit_ratio_table = perf.hit_ratio_table()
test_hit_ratio_table.show()
def iris_h2o_vs_sciKmeans():
# Connect to a pre-existing cluster
# connect to localhost:54321
iris_h2o = h2o.import_file(path=tests.locate("smalldata/iris/iris.csv"))
iris_sci = np.genfromtxt(tests.locate("smalldata/iris/iris.csv"),
delimiter=',')
iris_sci = iris_sci[:, 0:4]
s = [[4.9, 3.0, 1.4, 0.2], [5.6, 2.5, 3.9, 1.1], [6.5, 3.0, 5.2, 2.0]]
start = h2o.H2OFrame(s)
h2o_km = h2o.kmeans(x=iris_h2o[0:4],
k=3,
user_points=start,
standardize=False)
sci_km = KMeans(n_clusters=3, init=np.asarray(s), n_init=1)
sci_km.fit(iris_sci)
# Log.info("Cluster centers from H2O:")
print "Cluster centers from H2O:"
h2o_centers = h2o_km.centers()
print h2o_centers
# Log.info("Cluster centers from scikit:")
print "Cluster centers from scikit:"
sci_centers = sci_km.cluster_centers_.tolist()
print sci_centers
for hcenter, scenter in zip(h2o_centers, sci_centers):
for hpoint, spoint in zip(hcenter, scenter):
assert (hpoint - spoint) < 1e-10, "expected centers to be the same"
def separator():
path = "smalldata/jira/hexdev_29.csv"
fhex = h2o.import_file(tests.locate(path), sep=",")
fhex.summary()
fhex_col_summary = h2o.H2OConnection.get_json(
"Frames/" + urllib.quote(fhex._id) +
"/summary")["frames"][0]["columns"]
fhex_missing_count = sum([e["missing_count"] for e in fhex_col_summary])
assert fhex_missing_count == 0
fhex_wrong_separator = h2o.import_file(tests.locate(path), sep=";")
fhex_wrong_separator.summary()
fhex_wrong_separator_col_summary = h2o.H2OConnection.get_json(
"Frames/" + urllib.quote(fhex_wrong_separator._id) +
"/summary")["frames"][0]["columns"]
fhex_wrong_separator_missing_count = sum(
[e["missing_count"] for e in fhex_wrong_separator_col_summary])
assert fhex_wrong_separator_missing_count == fhex_wrong_separator._nrows * fhex_wrong_separator._ncols
try:
h2o.import_file(tests.locate(path), sep="--")
except ValueError:
pass
else:
assert False
def test_locate():
iris_path = h2o.locate("smalldata/iris/iris.csv")
try:
tests.locate("smalldata/iris/afilethatdoesnotexist.csv")
assert False, "Expected h2o.locate to raise a ValueError"
except ValueError:
assert True
def test_locate():
iris_path = h2o.locate("smalldata/iris/iris.csv")
try:
tests.locate("smalldata/iris/afilethatdoesnotexist.csv")
assert False, "Expected h2o.locate to raise a ValueError"
except ValueError:
assert True
def get_model_test():
prostate = h2o.import_file(path=tests.locate("smalldata/logreg/prostate.csv"))
r = prostate[0].runif()
train = prostate[r < 0.70]
test = prostate[r >= 0.70]
# Regression
regression_gbm1 = h2o.gbm(y=train[1], x=train[2:9], distribution="gaussian")
predictions1 = regression_gbm1.predict(test)
regression_gbm2 = h2o.get_model(regression_gbm1._id)
assert regression_gbm2._model_json['output']['model_category'] == "Regression"
predictions2 = regression_gbm2.predict(test)
for r in range(predictions1.nrow):
p1 = predictions1[r,0]
p2 = predictions2[r,0]
assert p1 == p2, "expected regression predictions to be the same for row {}, but got {} and {}".format(r, p1, p2)
# Binomial
train[1] = train[1].asfactor()
bernoulli_gbm1 = h2o.gbm(y=train[1], x=train[2:], distribution="bernoulli")
predictions1 = bernoulli_gbm1.predict(test)
bernoulli_gbm2 = h2o.get_model(bernoulli_gbm1._id)
assert bernoulli_gbm2._model_json['output']['model_category'] == "Binomial"
predictions2 = bernoulli_gbm2.predict(test)
for r in range(predictions1.nrow):
p1 = predictions1[r,0]
p2 = predictions2[r,0]
assert p1 == p2, "expected binomial predictions to be the same for row {}, but got {} and {}".format(r, p1, p2)
# Clustering
benign_h2o = h2o.import_file(path=tests.locate("smalldata/logreg/benign.csv"))
km_h2o = h2o.kmeans(x=benign_h2o, k=3)
benign_km = h2o.get_model(km_h2o._id)
assert benign_km._model_json['output']['model_category'] == "Clustering"
# Multinomial
train[4] = train[4].asfactor()
multinomial_dl1 = h2o.deeplearning(x=train[0:2], y=train[4], loss='CrossEntropy')
predictions1 = multinomial_dl1.predict(test)
multinomial_dl2 = h2o.get_model(multinomial_dl1._id)
assert multinomial_dl2._model_json['output']['model_category'] == "Multinomial"
predictions2 = multinomial_dl2.predict(test)
for r in range(predictions1.nrow):
p1 = predictions1[r,0]
p2 = predictions2[r,0]
assert p1 == p2, "expected multinomial predictions to be the same for row {0}, but got {1} and {2}" \
"".format(r, p1, p2)
def bernoulliGBM():
#Log.info("Importing prostate.csv data...\n")
prostate_train = h2o.import_file(path=tests.locate("smalldata/logreg/prostate_train.csv"))
#Log.info("Converting CAPSULE and RACE columns to factors...\n")
prostate_train["CAPSULE"] = prostate_train["CAPSULE"].asfactor()
#Log.info("H2O Summary of prostate frame:\n")
#prostate.summary()
# Import prostate_train.csv as numpy array for scikit comparison
trainData = np.loadtxt(tests.locate("smalldata/logreg/prostate_train.csv"), delimiter=',', skiprows=1)
trainDataResponse = trainData[:,0]
trainDataFeatures = trainData[:,1:]
ntrees = 100
learning_rate = 0.1
depth = 5
min_rows = 10
# Build H2O GBM classification model:
#Log.info(paste("H2O GBM with parameters:\ndistribution = 'bernoulli', ntrees = ", ntrees, ", max_depth = 5,
# min_rows = 10, learn_rate = 0.1\n", sep = ""))
gbm_h2o = h2o.gbm(x=prostate_train[1:], y=prostate_train["CAPSULE"], ntrees=ntrees, learn_rate=learning_rate,
max_depth=depth, min_rows=min_rows, distribution="bernoulli")
# Build scikit GBM classification model
#Log.info("scikit GBM with same parameters\n")
gbm_sci = ensemble.GradientBoostingClassifier(learning_rate=learning_rate, n_estimators=ntrees, max_depth=depth,
min_samples_leaf=min_rows, max_features=None)
gbm_sci.fit(trainDataFeatures,trainDataResponse)
#Log.info("Importing prostate_test.csv data...\n")
prostate_test = h2o.import_file(path=tests.locate("smalldata/logreg/prostate_test.csv"))
#Log.info("Converting CAPSULE and RACE columns to factors...\n")
prostate_test["CAPSULE"] = prostate_test["CAPSULE"].asfactor()
# Import prostate_test.csv as numpy array for scikit comparison
testData = np.loadtxt(tests.locate("smalldata/logreg/prostate_test.csv"), delimiter=',', skiprows=1)
testDataResponse = testData[:,0]
testDataFeatures = testData[:,1:]
# Score on the test data and compare results
# scikit
auc_sci = roc_auc_score(testDataResponse, gbm_sci.predict_proba(testDataFeatures)[:,1])
# h2o
gbm_perf = gbm_h2o.model_performance(prostate_test)
auc_h2o = gbm_perf.auc()
#Log.info(paste("scikit AUC:", auc_sci, "\tH2O AUC:", auc_h2o))
assert auc_h2o >= auc_sci, "h2o (auc) performance degradation, with respect to scikit"
def pubdev_1839():
train = h2o.import_file(tests.locate("smalldata/jira/pubdev_1839_repro_train.csv"))
test = h2o.import_file(tests.locate("smalldata/jira/pubdev_1839_repro_test.csv"))
glm0 = h2o.glm(x =train.drop("bikes"),
y =train ["bikes"],
validation_x=test .drop("bikes"),
validation_y=test ["bikes"],
family="poisson")
def deeplearning_autoencoder():
resp = 784
nfeatures = 20 # number of features (smallest hidden layer)
train_hex = h2o.upload_file(tests.locate("bigdata/laptop/mnist/train.csv.gz"))
train_hex[resp] = train_hex[resp].asfactor()
test_hex = h2o.upload_file(tests.locate("bigdata/laptop/mnist/test.csv.gz"))
test_hex[resp] = test_hex[resp].asfactor()
# split data into two parts
sid = train_hex[0].runif(1234)
# unsupervised data for autoencoder
train_unsupervised = train_hex[sid >= 0.5]
train_unsupervised.drop(resp)
train_unsupervised.describe()
# supervised data for drf
train_supervised = train_hex[sid < 0.5]
train_supervised.describe()
# train autoencoder
ae_model = h2o.deeplearning(x=train_unsupervised[0:resp],
activation="Tanh",
autoencoder=True,
hidden=[nfeatures],
epochs=1,
reproducible=True, #slow, turn off for real problems
seed=1234)
# conver train_supervised with autoencoder to lower-dimensional space
train_supervised_features = ae_model.deepfeatures(train_supervised[0:resp]._frame(), 0)
assert train_supervised_features.ncol == nfeatures, "Dimensionality of reconstruction is wrong!"
# Train DRF on extracted feature space
drf_model = h2o.random_forest(x=train_supervised_features[0:20],
y=train_supervised[resp],
ntrees=10,
min_rows=10,
seed=1234)
# Test the DRF model on the test set (processed through deep features)
test_features = ae_model.deepfeatures(test_hex[0:resp]._frame(), 0)
test_features = test_features.cbind(test_hex[resp])._frame()
# Confusion Matrix and assertion
cm = drf_model.confusion_matrix(test_features)
cm.show()
# 10% error +/- 0.001
assert abs(cm.cell_values[10][10] - 0.081) < 0.001, "Error. Expected 0.081, but got {0}".format(cm.cell_values[10][10])
def deeplearning_autoencoder():
resp = 784
nfeatures = 20 # number of features (smallest hidden layer)
train_hex = h2o.upload_file(tests.locate("bigdata/laptop/mnist/train.csv.gz"))
train_hex[resp] = train_hex[resp].asfactor()
test_hex = h2o.upload_file(tests.locate("bigdata/laptop/mnist/test.csv.gz"))
test_hex[resp] = test_hex[resp].asfactor()
# split data into two parts
sid = train_hex[0].runif(1234)
# unsupervised data for autoencoder
train_unsupervised = train_hex[sid >= 0.5]
train_unsupervised.drop(resp)
train_unsupervised.describe()
# supervised data for drf
train_supervised = train_hex[sid < 0.5]
train_supervised.describe()
# train autoencoder
ae_model = h2o.deeplearning(x=train_unsupervised[0:resp],
activation="Tanh",
autoencoder=True,
hidden=[nfeatures],
epochs=1,
reproducible=True, #slow, turn off for real problems
seed=1234)
# conver train_supervised with autoencoder to lower-dimensional space
train_supervised_features = ae_model.deepfeatures(train_supervised[0:resp]._frame(), 0)
assert train_supervised_features.ncol == nfeatures, "Dimensionality of reconstruction is wrong!"
# Train DRF on extracted feature space
drf_model = h2o.random_forest(x=train_supervised_features[0:20],
y=train_supervised[resp],
ntrees=10,
min_rows=10,
seed=1234)
# Test the DRF model on the test set (processed through deep features)
test_features = ae_model.deepfeatures(test_hex[0:resp]._frame(), 0)
test_features = test_features.cbind(test_hex[resp])._frame()
# Confusion Matrix and assertion
cm = drf_model.confusion_matrix(test_features)
cm.show()
# 10% error +/- 0.001
assert abs(cm.cell_values[10][10] - 0.082) < 0.001, "Error. Expected 0.082, but got {0}".format(cm.cell_values[10][10])
def shuffling_large():
print("Reading in Arcene training data for binomial modeling.")
train_data = h2o.upload_file(
path=tests.locate("smalldata/arcene/shuffle_test_version/arcene.csv"))
train_data_shuffled = h2o.upload_file(path=tests.locate(
"smalldata/arcene/shuffle_test_version/arcene_shuffled.csv"))
print("Create model on original Arcene dataset.")
h2o_model = h2o.glm(x=train_data[0:1000],
y=train_data[1000],
family="binomial",
lambda_search=True,
alpha=[0.5])
print("Create second model on original Arcene dataset.")
h2o_model_2 = h2o.glm(x=train_data[0:1000],
y=train_data[1000],
family="binomial",
lambda_search=True,
alpha=[0.5])
print("Create model on shuffled Arcene dataset.")
h2o_model_s = h2o.glm(x=train_data_shuffled[0:1000],
y=train_data_shuffled[1000],
family="binomial",
lambda_search=True,
alpha=[0.5])
print(
"Assert that number of predictors remaining and their respective coefficients are equal."
)
for x, y in zip(
h2o_model._model_json['output']['coefficients_table'].cell_values,
h2o_model_2._model_json['output']
['coefficients_table'].cell_values):
assert (type(x[1]) == type(y[1])) and (type(x[2]) == type(
y[2])), "coefficients should be the same type"
if isinstance(x[1], float):
assert abs(x[1] - y[1]) < 5e-10, "coefficients should be equal"
if isinstance(x[2], float):
assert abs(x[2] - y[2]) < 5e-10, "coefficients should be equal"
for x, y in zip(
h2o_model._model_json['output']['coefficients_table'].cell_values,
h2o_model_s._model_json['output']
['coefficients_table'].cell_values):
assert (type(x[1]) == type(y[1])) and (type(x[2]) == type(
y[2])), "coefficients should be the same type"
if isinstance(x[1], float):
assert abs(x[1] - y[1]) < 5e-10, "coefficients should be equal"
if isinstance(x[2], float):
assert abs(x[2] - y[2]) < 5e-10, "coefficients should be equal"
def headers():
headers = h2o.import_file(tests.locate("smalldata/airlines/allyears2k_headers_only.csv"))
headers_and = h2o.import_file(tests.locate("smalldata/airlines/allyears2k.zip"))
headers_and.set_names(headers.names)
print headers.names
print headers_and.names
assert headers.names == headers_and.names, "Expected the same column names but got {0} and {1}". \
format(headers.names, headers_and.names)
def frame_show():
iris = h2o.import_file(path=tests.locate("smalldata/iris/iris_wheader.csv"))
prostate = h2o.import_file(path=tests.locate("smalldata/prostate/prostate.csv.zip"))
airlines = h2o.import_file(path=tests.locate("smalldata/airlines/allyears2k.zip"))
iris.show()
prostate.show()
airlines.show()
def runif_check():
# Connect to a pre-existing cluster
uploaded_frame = h2o.upload_file(tests.locate("bigdata/laptop/mnist/train.csv.gz"))
r_u = uploaded_frame[0].runif(1234)
imported_frame = h2o.import_file(tests.locate("bigdata/laptop/mnist/train.csv.gz"))
r_i = imported_frame[0].runif(1234)
print "This demonstrates that seeding runif on identical frames with different chunk distributions provides " \
"different results. upload_file: {0}, import_frame: {1}.".format(r_u.mean(), r_i.mean())
def frame_as_list():
prostate = h2o.import_file(
path=tests.locate("smalldata/prostate/prostate.csv.zip"))
(prostate % 10).show()
(prostate[4] % 10).show()
airlines = h2o.import_file(
path=tests.locate("smalldata/airlines/allyears2k_headers.zip"))
(airlines["CRSArrTime"] % 100).show()
def pubdev_1839():
train = h2o.import_file(
tests.locate("smalldata/jira/pubdev_1839_repro_train.csv"))
test = h2o.import_file(
tests.locate("smalldata/jira/pubdev_1839_repro_test.csv"))
glm0 = h2o.glm(x=train.drop("bikes"),
y=train["bikes"],
validation_x=test.drop("bikes"),
validation_y=test["bikes"],
family="poisson")
def frame_show():
iris = h2o.import_file(
path=tests.locate("smalldata/iris/iris_wheader.csv"))
prostate = h2o.import_file(
path=tests.locate("smalldata/prostate/prostate.csv.zip"))
airlines = h2o.import_file(
path=tests.locate("smalldata/airlines/allyears2k.zip"))
iris.show()
prostate.show()
airlines.show()
def col_names_check():
iris_wheader = h2o.import_file(tests.locate("smalldata/iris/iris_wheader.csv"))
assert iris_wheader.col_names == ["sepal_len","sepal_wid","petal_len","petal_wid","class"], \
"Expected {0} for column names but got {1}".format(["sepal_len","sepal_wid","petal_len","petal_wid","class"],
iris_wheader.col_names)
iris = h2o.import_file(tests.locate("smalldata/iris/iris.csv"))
assert iris.col_names == ["C1","C2","C3","C4","C5"], "Expected {0} for column names but got " \
"{1}".format(["C1","C2","C3","C4","C5"], iris.col_names)
def kmeans_mllib():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
running_inside_h2o = tests.is_running_internal_to_h2o()
if running_inside_h2o:
hdfs_name_node = tests.get_h2o_internal_hdfs_name_node()
hdfs_cross_file = "/datasets/runit/BigCross.data"
print "Import BigCross.data from HDFS"
url = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_cross_file)
cross_h2o = h2o.import_file(url)
n = cross_h2o.nrow
err_mllib = np.genfromtxt(
tests.locate("smalldata/mllib_bench/bigcross_wcsse.csv"),
delimiter=",",
skip_header=1)
ncent = [int(err_mllib[r][0]) for r in range(len(err_mllib))]
for k in ncent:
print "Run k-means++ with k = {0} and max_iterations = 10".format(
k)
cross_km = h2o.kmeans(training_frame=cross_h2o,
x=cross_h2o,
k=k,
init="PlusPlus",
max_iterations=10,
standardize=False)
clust_mllib = np.genfromtxt(
tests.locate("smalldata/mllib_bench/bigcross_centers_" +
str(k) + ".csv"),
delimiter=",").tolist()
clust_h2o = cross_km.centers()
# Sort in ascending order by first dimension for comparison purposes
clust_mllib.sort(key=lambda x: x[0])
clust_h2o.sort(key=lambda x: x[0])
print "\nMLlib Cluster Centers:\n"
print clust_mllib
print "\nH2O Cluster Centers:\n"
print clust_h2o
wcsse_mllib = err_mllib[err_mllib[0:4, 0].tolist().index(k)][1]
wcsse_h2o = cross_km.tot_withinss() / n
print "\nMLlib Average Within-Cluster SSE: \n".format(wcsse_mllib)
print "H2O Average Within-Cluster SSE: \n".format(wcsse_h2o)
assert wcsse_h2o == wcsse_mllib, "Expected mllib and h2o to get the same wcsse. Mllib got {0}, and H2O " \
"got {1}".format(wcsse_mllib, wcsse_h2o)
def pubdev_1829():
train = h2o.import_file(path=tests.locate("smalldata/jira/gbm_checkpoint_train.csv"))
valid = h2o.import_file(path=tests.locate("smalldata/jira/gbm_checkpoint_valid.csv"))
predictors = ["displacement","power","weight","acceleration","year"]
response_col = "economy_20mpg"
distribution = "bernoulli"
train[response_col] = train[response_col].asfactor()
valid[response_col] = valid[response_col].asfactor()
ntrees1 = 5
max_depth1 = 5
min_rows1 = 10
model1 = h2o.gbm(x=train[predictors],
y=train[response_col],
ntrees=ntrees1,
max_depth=max_depth1,
min_rows=min_rows1,
score_each_iteration=True,
distribution=distribution,
validation_x=valid[predictors],
validation_y=valid[response_col])
ntrees2 = 10
max_depth2 = 5
min_rows2 = 10
model2 = h2o.gbm(x=train[predictors],
y=train[response_col],
ntrees=ntrees2,
max_depth=max_depth2,
min_rows=min_rows2,
distribution=distribution,
score_each_iteration=True,
validation_x=valid[predictors],
validation_y=valid[response_col],
checkpoint=model1._id)
model4 = h2o.gbm(x=train[predictors],
y=train[response_col],
ntrees=ntrees2,
max_depth=max_depth2,
min_rows=min_rows2,
distribution=distribution,
score_each_iteration=True,
validation_x=valid[predictors],
validation_y=valid[response_col])
assert model2.auc(valid=True)==model4.auc(valid=True), "Expected Model 2 AUC: {0} to be the same as Model 4 AUC: {1}".format(model2.auc(valid=True), model4.auc(valid=True))
assert model2.giniCoef(valid=True)==model4.giniCoef(valid=True), "Expected Model 2 Gini Coef {0} to be the same as Model 4 Gini Coef: {1}".format(model2.giniCoef(valid=True), model4.giniCoef(valid=True))
assert model2.logloss(valid=True)==model4.logloss(valid=True), "Expected Model 2 Log Loss: {0} to be the same as Model 4 Log Loss: {1}".format(model2.logloss(valid=True), model4.logloss(valid=True))
def javapredict_iris_drf():
# optional parameters
params = {'ntrees':100, 'max_depth':5, 'min_rows':10}
print "Parameter list:"
for k,v in zip(params.keys(), params.values()): print "{0}, {1}".format(k,v)
train = h2o.import_file(tests.locate("smalldata/iris/iris_train.csv"))
test = h2o.import_file(tests.locate("smalldata/iris/iris_train.csv"))
x = ["sepal_len","sepal_wid","petal_len","petal_wid"]
y = "species"
tests.javapredict("random_forest", "class", train, test, x, y, **params)
def javapredict_smallcat():
# optional parameters
params = {'ntrees':100, 'max_depth':5, 'min_rows':10}
print "Parameter list:"
for k,v in zip(params.keys(), params.values()): print "{0}, {1}".format(k,v)
train = h2o.upload_file(tests.locate("smalldata/iris/setosa_versicolor.csv"))
test = h2o.upload_file(tests.locate("smalldata/iris/virginica.csv"))
x = [0,1,2,4]
y = 3
tests.javapredict("random_forest", "numeric", train, test, x, y, **params)
def javapredict_cars():
# optional parameters
params = {'ntrees':5000, 'max_depth':10, 'min_rows':1, 'learn_rate':0.1, 'balance_classes':random.sample([True,False],1)[0]}
print "Parameter list:"
for k,v in zip(params.keys(), params.values()): print "{0}, {1}".format(k,v)
train = h2o.import_file(tests.locate("smalldata/junit/cars_nice_header.csv"))
test = h2o.import_file(tests.locate("smalldata/junit/cars_nice_header.csv"))
x = ["name","economy", "displacement","power","weight","acceleration","year"]
y = "cylinders"
tests.javapredict("gbm", "numeric", train, test, x, y, **params)
def javapredict_smallcat():
# optional parameters
params = {'epochs':100}
print "Parameter list:"
for k,v in zip(params.keys(), params.values()): print "{0}, {1}".format(k,v)
train = h2o.upload_file(tests.locate("smalldata/iris/setosa_versicolor.csv"))
test = h2o.upload_file(tests.locate("smalldata/iris/virginica.csv"))
x = [0,1,2,4]
y = 3
tests.javapredict("deeplearning", "numeric", train, test, x, y, **params)
def colname_set_basic():
print "Uploading iris data..."
no_headers = h2o.upload_file(tests.locate("smalldata/iris/iris.csv"))
headers_and = h2o.upload_file(
tests.locate("smalldata/iris/iris_header.csv"))
print no_headers.names
print headers_and.names
no_headers.set_names(headers_and.names)
assert no_headers.names == headers_and.names, "Expected the same column names but got {0} and {1}".\
format(no_headers.names, headers_and.names)
def javapredict_smallcat():
# optional parameters
params = {'epochs': 100}
print "Parameter list:"
for k, v in zip(params.keys(), params.values()):
print "{0}, {1}".format(k, v)
train = h2o.upload_file(
tests.locate("smalldata/iris/setosa_versicolor.csv"))
test = h2o.upload_file(tests.locate("smalldata/iris/virginica.csv"))
x = [0, 1, 2, 4]
y = 3
tests.javapredict("deeplearning", "numeric", train, test, x, y, **params)
def prostate():
h2o_data = h2o.upload_file(path=tests.locate("smalldata/logreg/prostate.csv"))
h2o_data.summary()
sm_data = pd.read_csv(tests.locate("smalldata/logreg/prostate.csv")).as_matrix()
sm_data_response = sm_data[:,1]
sm_data_features = sm_data[:,2:]
h2o_glm = h2o.glm(y=h2o_data[1], x=h2o_data[2:], family="binomial", nfolds=10, alpha=[0.5])
sm_glm = sm.GLM(endog=sm_data_response, exog=sm_data_features, family=sm.families.Binomial()).fit()
print "statsmodels null deviance {0}".format(sm_glm.null_deviance)
print "h2o null deviance {0}".format(h2o_glm.null_deviance())
assert abs(sm_glm.null_deviance - h2o_glm.null_deviance()) < 1e-5, "Expected null deviances to be the same"
def javapredict_smallcat():
# optional parameters
params = {'ntrees': 100, 'max_depth': 5, 'min_rows': 10}
print "Parameter list:"
for k, v in zip(params.keys(), params.values()):
print "{0}, {1}".format(k, v)
train = h2o.upload_file(
tests.locate("smalldata/iris/setosa_versicolor.csv"))
test = h2o.upload_file(tests.locate("smalldata/iris/virginica.csv"))
x = [0, 1, 2, 4]
y = 3
tests.javapredict("random_forest", "numeric", train, test, x, y, **params)